Dimensions of Explanatory Value in NLP Models

Kees van Deemter


Abstract
Performance on a dataset is often regarded as the key criterion for assessing NLP models. I argue for a broader perspective, which emphasizes scientific explanation. I draw on a long tradition in the philosophy of science, and on the Bayesian approach to assessing scientific theories, to argue for a plurality of criteria for assessing NLP models. To illustrate these ideas, I compare some recent models of language production with each other. I conclude by asking what it would mean for institutional policies if the NLP community took these ideas onboard.
Anthology ID:
2023.cl-3.6
Volume:
Computational Linguistics, Volume 49, Issue 3 - September 2023
Month:
September
Year:
2023
Address:
Cambridge, MA
Venue:
CL
SIG:
Publisher:
MIT Press
Note:
Pages:
749–761
Language:
URL:
https://aclanthology.org/2023.cl-3.6
DOI:
10.1162/coli_a_00480
Bibkey:
Cite (ACL):
Kees van Deemter. 2023. Dimensions of Explanatory Value in NLP Models. Computational Linguistics:749–761.
Cite (Informal):
Dimensions of Explanatory Value in NLP Models (van Deemter, CL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2023.cl-3.6.pdf